2
2.0
Apr 26, 2017
04/17
Apr 26, 2017
by
Samuel Rönnqvist; Niko Schenk; Christian Chiarcos
texts
eye 2
favorite 0
comment 0
We introduce an attention-based Bi-LSTM for Chinese implicit discourse relations and demonstrate that modeling argument pairs as a joint sequence can outperform word order-agnostic approaches. Our model benefits from a partial sampling scheme and is conceptually simple, yet achieves state-of-the-art performance on the Chinese Discourse Treebank. We also visualize its attention activity to illustrate the model's ability to selectively focus on the relevant parts of an input sequence.
Topics: Learning, Neural and Evolutionary Computing, Artificial Intelligence, Computing Research...
Source: http://arxiv.org/abs/1704.08092
2
2.0
Apr 25, 2017
04/17
Apr 25, 2017
by
Oswald Berthold; Verena Hafner
texts
eye 2
favorite 0
comment 0
We propose sensorimotor tappings, a new graphical technique that explicitly represents relations between the time steps of an agent's sensorimotor loop and a single training step of an adaptive model that the agent is using internally. In the simplest case this is a relation linking two time steps. In realistic cases these relations can extend over several time steps and over different sensory channels. The aim is to capture the footprint of information intake relative to the agent's current...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.07622
4
4.0
Apr 25, 2017
04/17
Apr 25, 2017
by
Xiaodong Gu; Hongyu Zhang; Dongmei Zhang; Sunghun Kim
texts
eye 4
favorite 0
comment 0
Computer programs written in one language are often required to be ported to other languages to support multiple devices and environments. When programs use language specific APIs (Application Programming Interfaces), it is very challenging to migrate these APIs to the corresponding APIs written in other languages. Existing approaches mine API mappings from projects that have corresponding versions in two languages. They rely on the sparse availability of bilingual projects, thus producing a...
Topics: Neural and Evolutionary Computing, Software Engineering, Computing Research Repository, Computation...
Source: http://arxiv.org/abs/1704.07734
7
7.0
Apr 25, 2017
04/17
Apr 25, 2017
by
Mariusz Bojarski; Philip Yeres; Anna Choromanska; Krzysztof Choromanski; Bernhard Firner; Lawrence Jackel; Urs Muller
texts
eye 7
favorite 0
comment 0
As part of a complete software stack for autonomous driving, NVIDIA has created a neural-network-based system, known as PilotNet, which outputs steering angles given images of the road ahead. PilotNet is trained using road images paired with the steering angles generated by a human driving a data-collection car. It derives the necessary domain knowledge by observing human drivers. This eliminates the need for human engineers to anticipate what is important in an image and foresee all the...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and...
Source: http://arxiv.org/abs/1704.07911
3
3.0
Apr 25, 2017
04/17
Apr 25, 2017
by
Long Jin; Justin Lazarow; Zhuowen Tu
texts
eye 3
favorite 0
comment 0
In this paper we propose introspective classifier learning (ICL) that emphasizes the importance of having a discriminative classifier empowered with generative capabilities. We develop a reclassification-by-synthesis algorithm to perform training using a formulation stemmed from the Bayes theory. Our classifier is able to iteratively: (1) synthesize pseudo-negative samples in the synthesis step; and (2) enhance itself by improving the classification in the reclassification step. The single...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and...
Source: http://arxiv.org/abs/1704.07816
2
2.0
Apr 25, 2017
04/17
Apr 25, 2017
by
Justin Lazarow; Long Jin; Zhuowen Tu
texts
eye 2
favorite 0
comment 0
We study unsupervised learning by developing introspective generative modeling (IGM) that attains a generator using progressively learned deep convolutional neural networks. The generator is itself a discriminator, capable of introspection: being able to self-evaluate the difference between its generated samples and the given training data. When followed by repeated discriminative learning, desirable properties of modern discriminative classifiers are directly inherited by the generator. IGM...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and...
Source: http://arxiv.org/abs/1704.07820
6
6.0
Apr 24, 2017
04/17
Apr 24, 2017
by
Marek Rei
texts
eye 6
favorite 0
comment 0
We propose a sequence labeling framework with a secondary training objective, learning to predict surrounding words for every word in the dataset. This language modeling objective incentivises the system to learn general-purpose patterns of semantic and syntactic composition, which are also useful for improving accuracy on different sequence labeling tasks. The architecture was evaluated on a range of datasets, covering the tasks of error detection in learner texts, named entity recognition,...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computation and Language
Source: http://arxiv.org/abs/1704.07156
2
2.0
Apr 24, 2017
04/17
Apr 24, 2017
by
Irina Petrova; Arina Buzdalova
texts
eye 2
favorite 0
comment 0
Efficiency of single-objective optimization can be improved by introducing some auxiliary objectives. Ideally, auxiliary objectives should be helpful. However, in practice, objectives may be efficient on some optimization stages but obstructive on others. In this paper we propose a modification of the EA+RL method which dynamically selects optimized objectives using reinforcement learning. The proposed modification prevents from losing the best found solution. We analysed the proposed...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.07187
3
3.0
Apr 24, 2017
04/17
Apr 24, 2017
by
Sri Harsha Dumpala; Rupayan Chakraborty; Sunil Kumar Kopparapu
texts
eye 3
favorite 0
comment 0
Recurrent neural network (RNN) are being extensively used over feed-forward neural networks (FFNN) because of their inherent capability to capture temporal relationships that exist in the sequential data such as speech. This aspect of RNN is advantageous especially when there is no a priori knowledge about the temporal correlations within the data. However, RNNs require large amount of data to learn these temporal correlations, limiting their advantage in low resource scenarios. It is not...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.07055
2
2.0
Apr 23, 2017
04/17
Apr 23, 2017
by
Rauca D. Gaina; Simon M. Lucas; Diego Perez-Liebana
texts
eye 2
favorite 0
comment 0
While Monte Carlo Tree Search and closely related methods have dominated General Video Game Playing, recent research has demonstrated the promise of Rolling Horizon Evolutionary Algorithms as an interesting alternative. However, there is little attention paid to population initialization techniques in the setting of general real-time video games. Therefore, this paper proposes the use of population seeding to improve the performance of Rolling Horizon Evolution and presents the results of two...
Topics: Neural and Evolutionary Computing, Artificial Intelligence, Computing Research Repository
Source: http://arxiv.org/abs/1704.06942
2
2.0
Apr 23, 2017
04/17
Apr 23, 2017
by
Jacob Andreas; Anca Dragan; Dan Klein
texts
eye 2
favorite 0
comment 0
Several approaches have recently been proposed for learning decentralized deep multiagent policies that coordinate via a differentiable communication channel. While these policies are effective for many tasks, interpretation of their induced communication strategies has remained a challenge. Here we propose to interpret agents' messages by translating them. Unlike in typical machine translation problems, we have no parallel data to learn from. Instead we develop a translation model based on the...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Computation and Language
Source: http://arxiv.org/abs/1704.06960
2
2.0
Apr 23, 2017
04/17
Apr 23, 2017
by
Kartik Goyal; Chris Dyer; Taylor Berg-Kirkpatrick
texts
eye 2
favorite 0
comment 0
We demonstrate that a continuous relaxation of the argmax operation can be used to create a differentiable approximation to greedy decoding for sequence-to-sequence (seq2seq) models. By incorporating this approximation into the scheduled sampling training procedure (Bengio et al., 2015)--a well-known technique for correcting exposure bias--we introduce a new training objective that is continuous and differentiable everywhere and that can provide informative gradients near points where previous...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computation and Language
Source: http://arxiv.org/abs/1704.06970
2
2.0
Apr 22, 2017
04/17
Apr 22, 2017
by
Fabio D'Andreagiovanni; Jonatan Krolikowski; Jonad Pulaj
texts
eye 2
favorite 0
comment 0
We investigate the Robust Multiperiod Network Design Problem, a generalization of the classical Capacitated Network Design Problem that additionally considers multiple design periods and provides solutions protected against traffic uncertainty. Given the intrinsic difficulty of the problem, which proves challenging even for state-of-the art commercial solvers, we propose a hybrid primal heuristic based on the combination of ant colony optimization and an exact large neighborhood search....
Topics: Optimization and Control, Computing Research Repository, Networking and Internet Architecture,...
Source: http://arxiv.org/abs/1704.06847
5
5.0
Apr 21, 2017
04/17
Apr 21, 2017
by
Sebastien C. Wong; Victor Stamatescu; Adam Gatt; David Kearney; Ivan Lee; Mark D. McDonnell
texts
eye 5
favorite 0
comment 0
This paper addresses the problem of online tracking and classification of multiple objects in an image sequence. Our proposed solution is to first track all objects in the scene without relying on object-specific prior knowledge, which in other systems can take the form of hand-crafted features or user-based track initialization. We then classify the tracked objects with a fast-learning image classifier that is based on a shallow convolutional neural network architecture and demonstrate that...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and Pattern...
Source: http://arxiv.org/abs/1704.06415
4
4.0
Apr 21, 2017
04/17
Apr 21, 2017
by
Dylan Richard Muir
texts
eye 4
favorite 0
comment 0
Recurrent neural network architectures can have useful computational properties, with complex temporal dynamics. However, evaluation of recurrent dynamic architectures requires solution of systems of differential equations, and the number of evaluations required to determine their response to a given input can vary with the input, or can be indeterminate altogether in the case of oscillations or instability. In feed-forward networks, by contrast, only a single pass through the network is needed...
Topics: Neural and Evolutionary Computing, Neurons and Cognition, Computing Research Repository,...
Source: http://arxiv.org/abs/1704.06645
9
9.0
Apr 21, 2017
04/17
Apr 21, 2017
by
Jonathon Cai; Richard Shin; Dawn Song
texts
eye 9
favorite 0
comment 0
Empirically, neural networks that attempt to learn programs from data have exhibited poor generalizability. Moreover, it has traditionally been difficult to reason about the behavior of these models beyond a certain level of input complexity. In order to address these issues, we propose augmenting neural architectures with a key abstraction: recursion. As an application, we implement recursion in the Neural Programmer-Interpreter framework on four tasks: grade-school addition, bubble sort,...
Topics: Learning, Neural and Evolutionary Computing, Programming Languages, Computing Research Repository
Source: http://arxiv.org/abs/1704.06611
2
2.0
Apr 21, 2017
04/17
Apr 21, 2017
by
Fabio D'Andreagiovanni
texts
eye 2
favorite 0
comment 0
Base station cooperation (BSC) has recently arisen as a promising way to increase the capacity of a wireless network. Implementing BSC adds a new design dimension to the classical wireless network design problem: how to define the subset of base stations (clusters) that coordinate to serve a user. Though the problem of forming clusters has been extensively discussed from a technical point of view, there is still a lack of effective optimization models for its representation and algorithms for...
Topics: Optimization and Control, Computing Research Repository, Networking and Internet Architecture,...
Source: http://arxiv.org/abs/1704.06684
2
2.0
Apr 21, 2017
04/17
Apr 21, 2017
by
Jindřich Libovický; Jindřich Helcl
texts
eye 2
favorite 0
comment 0
Modeling attention in neural multi-source sequence-to-sequence learning remains a relatively unexplored area, despite its usefulness in tasks that incorporate multiple source languages or modalities. We propose two novel approaches to combine the outputs of attention mechanisms over each source sequence, flat and hierarchical. We compare the proposed methods with existing techniques and present results of systematic evaluation of those methods on the WMT16 Multimodal Translation and Automatic...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Computation and Language
Source: http://arxiv.org/abs/1704.06567
2
2.0
Apr 20, 2017
04/17
Apr 20, 2017
by
Min Lin
texts
eye 2
favorite 0
comment 0
Softmax GAN is a novel variant of Generative Adversarial Network (GAN). The key idea of Softmax GAN is to replace the classification loss in the original GAN with a softmax cross-entropy loss in the sample space of one single batch. In the adversarial learning of $N$ real training samples and $M$ generated samples, the target of discriminator training is to distribute all the probability mass to the real samples, each with probability $\frac{1}{M}$, and distribute zero probability to generated...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.06191
5
5.0
Apr 19, 2017
04/17
Apr 19, 2017
by
Hongyu Guo; Colin Cherry; Jiang Su
texts
eye 5
favorite 0
comment 0
We propose a multi-view network for text classification. Our method automatically creates various views of its input text, each taking the form of soft attention weights that distribute the classifier's focus among a set of base features. For a bag-of-words representation, each view focuses on a different subset of the text's words. Aggregating many such views results in a more discriminative and robust representation. Through a novel architecture that both stacks and concatenates views, we...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computation and Language
Source: http://arxiv.org/abs/1704.05907
3
3.0
Apr 19, 2017
04/17
Apr 19, 2017
by
Simon Wessing; Mike Preuss
texts
eye 3
favorite 0
comment 0
Efficient global optimization is a popular algorithm for the optimization of expensive multimodal black-box functions. One important reason for its popularity is its theoretical foundation of global convergence. However, as the budgets in expensive optimization are very small, the asymptotic properties only play a minor role and the algorithm sometimes comes off badly in experimental comparisons. Many alternative variants have therefore been proposed over the years. In this work, we show...
Topics: Optimization and Control, Neural and Evolutionary Computing, Computing Research Repository,...
Source: http://arxiv.org/abs/1704.05724
2
2.0
Apr 18, 2017
04/17
Apr 18, 2017
by
Y. Cem Subakan; Paris Smaragdis
texts
eye 2
favorite 0
comment 0
In this paper, we propose a new Recurrent Neural Network (RNN) architecture. The novelty is simple: We use diagonal recurrent matrices instead of full. This results in better test likelihood and faster convergence compared to regular full RNNs in most of our experiments. We show the benefits of using diagonal recurrent matrices with popularly used LSTM and GRU architectures as well as with the vanilla RNN architecture, on four standard symbolic music datasets.
Topics: Learning, Machine Learning, Neural and Evolutionary Computing, Statistics, Computing Research...
Source: http://arxiv.org/abs/1704.05420
3
3.0
Apr 18, 2017
04/17
Apr 18, 2017
by
Elliot Meyerson; Risto Miikkulainen
texts
eye 3
favorite 0
comment 0
Behavior domination is proposed as a tool for understanding and harnessing the power of evolutionary systems to discover and exploit useful stepping stones. Novelty search has shown promise in overcoming deception by collecting diverse stepping stones, and several algorithms have been proposed that combine novelty with a more traditional fitness measure to refocus search and help novelty search scale to more complex domains. However, combinations of novelty and fitness do not necessarily...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.05554
2
2.0
Apr 18, 2017
04/17
Apr 18, 2017
by
Jean-Charles Vialatte; François Leduc-Primeau
texts
eye 2
favorite 0
comment 0
For many types of integrated circuits, accepting larger failure rates in computations can be used to improve energy efficiency. We study the performance of faulty implementations of certain deep neural networks based on pessimistic and optimistic models of the effect of hardware faults. After identifying the impact of hyperparameters such as the number of layers on robustness, we study the ability of the network to compensate for computational failures through an increase of the network size....
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.05396
2
2.0
Apr 17, 2017
04/17
Apr 17, 2017
by
Joao Paulo Papa; Gustavo Henrique Rosa; Douglas Rodrigues; Xin-She Yang
texts
eye 2
favorite 0
comment 0
Optimization techniques play an important role in several scientific and real-world applications, thus becoming of great interest for the community. As a consequence, a number of open-source libraries are available in the literature, which ends up fostering the research and development of new techniques and applications. In this work, we present a new library for the implementation and fast prototyping of nature-inspired techniques called LibOPT. Currently, the library implements 15 techniques...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.05174
3
3.0
Apr 17, 2017
04/17
Apr 17, 2017
by
Joost Huizinga; Kenneth O. Stanley; Jeff Clune
texts
eye 3
favorite 0
comment 0
Natural evolution has produced a tremendous diversity of functional organisms. Many believe an essential component of this process was the evolution of evolvability, whereby evolution speeds up its ability to innovate by generating a more adaptive pool of offspring. One hypothesized mechanism for evolvability is developmental canalization, wherein certain dimensions of variation become more likely to be traversed and others are prevented from being explored (e.g. offspring tend to have...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.05143
4
4.0
Apr 17, 2017
04/17
Apr 17, 2017
by
Jan Žegklitz; Petr Pošík
texts
eye 4
favorite 0
comment 0
We propose a new type of leaf node for use in Symbolic Regression (SR) that performs linear combinations of feature variables (LCF). These nodes can be handled in three different modes -- an unsynchronized mode, where all LCFs are free to change on their own, a synchronized mode, where LCFs are sorted into groups in which they are forced to be identical throughout the whole individual, and a globally synchronized mode, which is similar to the previous mode but the grouping is done across the...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.05134
4
4.0
Apr 17, 2017
04/17
Apr 17, 2017
by
Nikolaos Antoniadis; Angelo Sifaleras
texts
eye 4
favorite 0
comment 0
In this paper, we study various parallelization schemes for the Variable Neighborhood Search (VNS) metaheuristic on a CPU-GPU system via OpenMP and OpenACC. A hybrid parallel VNS method is applied to recent benchmark problem instances for the multi-product dynamic lot sizing problem with product returns and recovery, which appears in reverse logistics and is known to be NP-hard. We report our findings regarding these parallelization approaches and present promising computational results.
Topics: Neural and Evolutionary Computing, Distributed, Parallel, and Cluster Computing, Computing Research...
Source: http://arxiv.org/abs/1704.05132
5
5.0
Apr 17, 2017
04/17
Apr 17, 2017
by
Grant Dick
texts
eye 5
favorite 0
comment 0
Symbolic regression via genetic programming is a flexible approach to machine learning that does not require up-front specification of model structure. However, traditional approaches to symbolic regression require the use of protected operators, which can lead to perverse model characteristics and poor generalisation. In this paper, we revisit interval arithmetic as one possible solution to allow genetic programming to perform regression using unprotected operators. Using standard benchmarks,...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.04998
2
2.0
Apr 17, 2017
04/17
Apr 17, 2017
by
Zhitao Gong; Wenlu Wang; Wei-Shinn Ku
texts
eye 2
favorite 0
comment 0
Adversarial attack has cast a shadow on the massive success of deep neural networks. Despite being almost visually identical to the clean data, the adversarial images can fool deep neural networks into wrong predictions with very high confidence. In this paper, however, we show that we can build a simple binary classifier separating the adversarial apart from the clean data with accuracy over 99%. We also empirically show that the binary classifier is robust to a second-round adversarial...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.04960
4
4.0
Apr 17, 2017
04/17
Apr 17, 2017
by
Tinnaluk Rutjanisarakul; Thiradet Jiarasuksakun
texts
eye 4
favorite 0
comment 0
A sport tournament problem is considered the Traveling Tournament Problem (TTP). One interesting type is the mirrored Traveling Tournament Problem (mTTP). The objective of the problem is to minimize either the total number of traveling or the total distances of traveling or both. This research aims to find an optimized solution of the mirrored Traveling Tournament Problem with minimum total number of traveling. The solutions consisting of traveling and scheduling tables are solved by using...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.04879
3
3.0
Apr 15, 2017
04/17
Apr 15, 2017
by
Fabio D'Andreagiovanni
texts
eye 3
favorite 0
comment 0
Over the last decade, wireless networks have experienced an impressive growth and now play a main role in many telecommunications systems. As a consequence, scarce radio resources, such as frequencies, became congested and the need for effective and efficient assignment methods arose. In this work, we present a Genetic Algorithm for solving large instances of the Power, Frequency and Modulation Assignment Problem, arising in the design of wireless networks. To our best knowledge, this is the...
Topics: Optimization and Control, Neural and Evolutionary Computing, Computing Research Repository,...
Source: http://arxiv.org/abs/1704.05367
2
2.0
Apr 15, 2017
04/17
Apr 15, 2017
by
Fabio D'Andreagiovanni; Antonella Nardin; Enrico Natalizio
texts
eye 2
favorite 0
comment 0
We consider the problem of optimally designing a body wireless sensor network, while taking into account the uncertainty of data generation of biosensors. Since the related min-max robustness Integer Linear Programming (ILP) problem can be difficult to solve even for state-of-the-art commercial optimization solvers, we propose an original heuristic for its solution. The heuristic combines deterministic and probabilistic variable fixing strategies, guided by the information coming from...
Topics: Optimization and Control, Neural and Evolutionary Computing, Networking and Internet Architecture,...
Source: http://arxiv.org/abs/1704.04640
2
2.0
Apr 14, 2017
04/17
Apr 14, 2017
by
Maxim Buzdalov; Benjamin Doerr
texts
eye 2
favorite 0
comment 0
The $(1+(\lambda,\lambda))$ genetic algorithm, first proposed at GECCO 2013, showed a surprisingly good performance on so me optimization problems. The theoretical analysis so far was restricted to the OneMax test function, where this GA profited from the perfect fitness-distance correlation. In this work, we conduct a rigorous runtime analysis of this GA on random 3-SAT instances in the planted solution model having at least logarithmic average degree, which are known to have a weaker fitness...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.04366
3
3.0
Apr 13, 2017
04/17
Apr 13, 2017
by
Brendan Cody-Kenny; Michael Fenton; Adrian Ronayne; Eoghan Considine; Thomas McGuire; Michael O'Neill
texts
eye 3
favorite 0
comment 0
The primary aim of automated performance improvement is to reduce the running time of programs while maintaining (or improving on) functionality. In this paper, Genetic Programming is used to find performance improvements in regular expressions for an array of target programs, representing the first application of automated software improvement for run-time performance in the Regular Expression language. This particular problem is interesting as there may be many possible alternative regular...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.04119
3
3.0
Apr 12, 2017
04/17
Apr 12, 2017
by
Timo Hackel; Nikolay Savinov; Lubor Ladicky; Jan D. Wegner; Konrad Schindler; Marc Pollefeys
texts
eye 3
favorite 0
comment 0
This paper presents a new 3D point cloud classification benchmark data set with over four billion manually labelled points, meant as input for data-hungry (deep) learning methods. We also discuss first submissions to the benchmark that use deep convolutional neural networks (CNNs) as a work horse, which already show remarkable performance improvements over state-of-the-art. CNNs have become the de-facto standard for many tasks in computer vision and machine learning like semantic segmentation...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and...
Source: http://arxiv.org/abs/1704.03847
25
25
Apr 10, 2017
04/17
Apr 10, 2017
by
Alex Graves; Marc G. Bellemare; Jacob Menick; Remi Munos; Koray Kavukcuoglu
texts
eye 25
favorite 0
comment 0
We introduce a method for automatically selecting the path, or syllabus, that a neural network follows through a curriculum so as to maximise learning efficiency. A measure of the amount that the network learns from each data sample is provided as a reward signal to a nonstationary multi-armed bandit algorithm, which then determines a stochastic syllabus. We consider a range of signals derived from two distinct indicators of learning progress: rate of increase in prediction accuracy, and rate...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.03003
5
5.0
Apr 10, 2017
04/17
Apr 10, 2017
by
Carlos Florensa; Yan Duan; Pieter Abbeel
texts
eye 5
favorite 0
comment 0
Deep reinforcement learning has achieved many impressive results in recent years. However, tasks with sparse rewards or long horizons continue to pose significant challenges. To tackle these important problems, we propose a general framework that first learns useful skills in a pre-training environment, and then leverages the acquired skills for learning faster in downstream tasks. Our approach brings together some of the strengths of intrinsic motivation and hierarchical methods: the learning...
Topics: Learning, Neural and Evolutionary Computing, Artificial Intelligence, Computing Research...
Source: http://arxiv.org/abs/1704.03012
2
2.0
Apr 10, 2017
04/17
Apr 10, 2017
by
Asit Mishra; Jeffrey J Cook; Eriko Nurvitadhi; Debbie Marr
texts
eye 2
favorite 0
comment 0
For computer vision applications, prior works have shown the efficacy of reducing the numeric precision of model parameters (network weights) in deep neural networks but also that reducing the precision of activations hurts model accuracy much more than reducing the precision of model parameters. We study schemes to train networks from scratch using reduced-precision activations without hurting the model accuracy. We reduce the precision of activation maps (along with model parameters) using a...
Topics: Learning, Neural and Evolutionary Computing, Artificial Intelligence, Computing Research...
Source: http://arxiv.org/abs/1704.03079
5
5.0
Apr 9, 2017
04/17
Apr 9, 2017
by
Avanti Shrikumar; Peyton Greenside; Anshul Kundaje
texts
eye 5
favorite 0
comment 0
The purported "black box"' nature of neural networks is a barrier to adoption in applications where interpretability is essential. Here we present DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction of a neural network on a specific input by backpropagating the contributions of all neurons in the network to every feature of the input. DeepLIFT compares the activation of each neuron to its 'reference activation' and assigns contribution scores...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and...
Source: http://arxiv.org/abs/1704.02685
4
4.0
Apr 7, 2017
04/17
Apr 7, 2017
by
Mengyuan Wu; Ke Li; Sam Kwong; Qingfu Zhang
texts
eye 4
favorite 0
comment 0
The decomposition-based method has been recognized as a major approach for multi-objective optimization. It decomposes a multi-objective optimization problem into several single-objective optimization subproblems, each of which is usually defined as a scalarizing function using a weight vector. Due to the characteristics of the contour line of a particular scalarizing function, the performance of the decomposition-based method strongly depends on the Pareto front's shape by merely using a...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.02340
4
4.0
Apr 7, 2017
04/17
Apr 7, 2017
by
Yaoyuan Zhang; Zhenxu Ye; Yansong Feng; Dongyan Zhao; Rui Yan
texts
eye 4
favorite 0
comment 0
Sentence simplification reduces semantic complexity to benefit people with language impairments. Previous simplification studies on the sentence level and word level have achieved promising results but also meet great challenges. For sentence-level studies, sentences after simplification are fluent but sometimes are not really simplified. For word-level studies, words are simplified but also have potential grammar errors due to different usages of words before and after simplification. In this...
Topics: Neural and Evolutionary Computing, Artificial Intelligence, Computing Research Repository,...
Source: http://arxiv.org/abs/1704.02312
5
5.0
Apr 6, 2017
04/17
Apr 6, 2017
by
Raluca Necula; Mihaela Breaban; Madalina Raschip
texts
eye 5
favorite 0
comment 0
The Dynamic Vehicle Routing Problem with Time Windows (DVRPTW) is an extension of the well-known Vehicle Routing Problem (VRP), which takes into account the dynamic nature of the problem. This aspect requires the vehicle routes to be updated in an ongoing manner as new customer requests arrive in the system and must be incorporated into an evolving schedule during the working day. Besides the vehicle capacity constraint involved in the classical VRP, DVRPTW considers in addition time windows,...
Topics: Neural and Evolutionary Computing, Artificial Intelligence, Computing Research Repository
Source: http://arxiv.org/abs/1704.01859
2
2.0
Apr 6, 2017
04/17
Apr 6, 2017
by
Rishidev Chaudhuri; Ila Fiete
texts
eye 2
favorite 0
comment 0
The brain must robustly store a large number of memories, corresponding to the many events and scenes a person encounters over a lifetime. However, the number of memory states in existing neural network models either grows weakly with network size or recall performance fails catastrophically with vanishingly little noise. Here we show that it is possible to construct an associative content-addressable memory (ACAM) with exponentially many stable states and robust error-correction. The network...
Topics: Quantitative Biology, Neurons and Cognition, Neural and Evolutionary Computing, Computing Research...
Source: http://arxiv.org/abs/1704.02019
3
3.0
Apr 6, 2017
04/17
Apr 6, 2017
by
Mohammad Javad Shafiee; Elnaz Barshan; Alexander Wong
texts
eye 3
favorite 0
comment 0
A promising paradigm for achieving highly efficient deep neural networks is the idea of evolutionary deep intelligence, which mimics biological evolution processes to progressively synthesize more efficient networks. A crucial design factor in evolutionary deep intelligence is the genetic encoding scheme used to simulate heredity and determine the architectures of offspring networks. In this study, we take a deeper look at the notion of synaptic cluster-driven evolution of deep neural networks...
Topics: Computer Vision and Pattern Recognition, Computing Research Repository, Machine Learning, Neural...
Source: http://arxiv.org/abs/1704.02081
2
2.0
Apr 5, 2017
04/17
Apr 5, 2017
by
Alec Radford; Rafal Jozefowicz; Ilya Sutskever
texts
eye 2
favorite 0
comment 0
We explore the properties of byte-level recurrent language models. When given sufficient amounts of capacity, training data, and compute time, the representations learned by these models include disentangled features corresponding to high-level concepts. Specifically, we find a single unit which performs sentiment analysis. These representations, learned in an unsupervised manner, achieve state of the art on the binary subset of the Stanford Sentiment Treebank. They are also very data...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computation and Language
Source: http://arxiv.org/abs/1704.01444
6
6.0
Apr 5, 2017
04/17
Apr 5, 2017
by
Yoav Levine; David Yakira; Nadav Cohen; Amnon Shashua
texts
eye 6
favorite 0
comment 0
Deep convolutional networks have witnessed unprecedented success in various machine learning applications. Formal understanding on what makes these networks so successful is gradually unfolding, but for the most part there are still significant mysteries to unravel. The inductive bias, which reflects prior knowledge embedded in the network architecture, is one of them. In this work, we establish a fundamental connection between the fields of quantum physics and deep learning. We use this...
Topics: Learning, Neural and Evolutionary Computing, Quantum Physics, Computing Research Repository
Source: http://arxiv.org/abs/1704.01552
3
3.0
Apr 5, 2017
04/17
Apr 5, 2017
by
Ji Young Lee; Franck Dernoncourt; Peter Szolovits
texts
eye 3
favorite 0
comment 0
Over 50 million scholarly articles have been published: they constitute a unique repository of knowledge. In particular, one may infer from them relations between scientific concepts, such as synonyms and hyponyms. Artificial neural networks have been recently explored for relation extraction. In this work, we continue this line of work and present a system based on a convolutional neural network to extract relations. Our model ranked first in the SemEval-2017 task 10 (ScienceIE) for relation...
Topics: Computing Research Repository, Machine Learning, Computation and Language, Neural and Evolutionary...
Source: http://arxiv.org/abs/1704.01523
2
2.0
Apr 4, 2017
04/17
Apr 4, 2017
by
Sanjay Ganapathy; Swagath Venkataramani; Balaraman Ravindran; Anand Raghunathan
texts
eye 2
favorite 0
comment 0
Deep Neural Networks (DNNs) have advanced the state-of-the-art in a variety of machine learning tasks and are deployed in increasing numbers of products and services. However, the computational requirements of training and evaluating large-scale DNNs are growing at a much faster pace than the capabilities of the underlying hardware platforms that they are executed upon. In this work, we propose Dynamic Variable Effort Deep Neural Networks (DyVEDeep) to reduce the computational requirements of...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and...
Source: http://arxiv.org/abs/1704.01137
3
3.0
Apr 4, 2017
04/17
Apr 4, 2017
by
Rajkumar Ramamurthy; Christian Bauckhage; Krisztian Buza; Stefan Wrobel
texts
eye 3
favorite 0
comment 0
Echo state networks are simple recurrent neural networks that are easy to implement and train. Despite their simplicity, they show a form of memory and can predict or regenerate sequences of data. We make use of this property to realize a novel neural cryptography scheme. The key idea is to assume that Alice and Bob share a copy of an echo state network. If Alice trains her copy to memorize a message, she can communicate the trained part of the network to Bob who plugs it into his copy to...
Topics: Cryptography and Security, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.01046
